This Kaggle is a project from the course [T81-855: Applications of Deep Learning at Washington University in St. Louis](https://sites.wustl.edu/jeffheaton/t81-558/). All students must create a Kaggle account and submit a solution. If you are a student, once you have submitted your solution entry log into Canvas (at WUSTL) and submit a single file telling me your Kaggle name on the leaderboard (you do not need to register to Kaggle with your real name). This competition will be visible to the public, so there may be non-student submissions as well as from the students.

For this competition, you will determine if a person is wearing glasses or not.  However, your test subjects are not real people.  A Generative Adversarial Neural Network (GAN) created all of the people that you see in this competition.  The GAN network creates these images using a 512 number latent vector.  The Kaggle assignment provides both the latent vectors and the faces produced by those vectors.  Both may be useful to you in classifying if someone is wearing glasses or not.

![GANs Glasses or No Glasses](https://data.heatonresearch.com/images/wustl/kaggle/kaggle-faces-glasses.png)

Glasses come in many different forms, make sure you can identify them all.  The image below shows a sampling of some of the types of glasses contained in the dataset.

![GANs Glasses or No Glasses](https://data.heatonresearch.com/images/wustl/kaggle/kaggle-faces-glasses-2.png)